DemonGatanjieuandClaude Opus 5.5
414e76c935
- header_words.py: modelspec.trigger_phrase, else the tags most training pictures share (ss_tag_frequency, generic ones left out); the scanner keeps them as anomalous_header_words when Civitai gives no trigger words, metadata gives headerWords, model search finds them. - model_kind: Flux Schnell told from Dev (no guidance_in), Z-Image from Lumina 2 (caption embedder width, a GGUF by parameter count); RULES 3 so kept header answers are read again. - api/model_guide.py + model_profiles.json: GET /anomalous/model_guide for the model details (example settings, header words, the text encoder and VAE a diffusion models file needs, found by name), and get_model's header_words and usage for the AI. - model_advice.example_settings gives the author's example settings as values; author_examples says them in words as before. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
72 lines
3.4 KiB
Python
72 lines
3.4 KiB
Python
"""Words a LoRA's own file suggests for the prompt, for a LoRA Civitai gives none: the trigger
|
|
phrase its maker wrote (modelspec.trigger_phrase), else the tags most of its training pictures
|
|
share (kohya's ss_tag_frequency), tags any picture could have left out. A guess, shown as one and
|
|
never mixed into Civitai's trainedWords. The scanner keeps them in the .info it writes
|
|
(anomalous_header_words); the model details and the AI read a LoRA scanned before that at once.
|
|
Reads the header only (model_kind.read_head). No imports from ComfyUI.
|
|
"""
|
|
|
|
import json
|
|
|
|
try:
|
|
from .model_kind import classify, read_head
|
|
except ImportError: # the standalone scanner imports this file on its own
|
|
from model_kind import classify, read_head
|
|
|
|
MOST = 5
|
|
SHARE = 0.5 # in at least half as many pictures as the most used tag
|
|
LONGEST = 60
|
|
# Tags that say nothing of what a LoRA adds: how many people, framing, plain backgrounds, quality words.
|
|
GENERIC = frozenset((
|
|
"1girl", "1boy", "2girls", "2boys", "3girls", "multiple girls", "multiple boys", "solo", "solo focus",
|
|
"female focus", "male focus", "looking at viewer", "looking at another", "looking away", "simple background",
|
|
"white background", "grey background", "gray background", "black background", "transparent background",
|
|
"smile", "open mouth", "closed mouth", "parted lips", "blush", "upper body", "full body", "cowboy shot",
|
|
"portrait", "close-up", "standing", "sitting", "long hair", "short hair", "medium hair", "very long hair",
|
|
"breasts", "small breasts", "medium breasts", "large breasts", "outdoors", "indoors", "day", "night",
|
|
"monochrome", "greyscale", "masterpiece", "best quality", "high quality", "highres", "absurdres",
|
|
"lowres", "score_9", "score_8_up", "score_7_up",
|
|
))
|
|
|
|
|
|
def _split(text):
|
|
return [part.strip() for part in str(text).split(",") if part.strip()]
|
|
|
|
|
|
def _counts(text):
|
|
"""{tag: how many training pictures have it} from ss_tag_frequency ({folder: {tag: count}})."""
|
|
try:
|
|
folders = json.loads(text or "{}")
|
|
except ValueError:
|
|
return {}
|
|
counts = {}
|
|
for tags in folders.values() if isinstance(folders, dict) else ():
|
|
for tag, count in tags.items() if isinstance(tags, dict) else ():
|
|
name = str(tag).strip()
|
|
if name and isinstance(count, (int, float)) and not isinstance(count, bool):
|
|
counts[name] = counts.get(name, 0) + count
|
|
return counts
|
|
|
|
|
|
def from_meta(meta):
|
|
"""Up to MOST words from a safetensors header's __metadata__ (its values are strings)."""
|
|
phrase = _split(meta.get("modelspec.trigger_phrase") or "")
|
|
if phrase:
|
|
return [word[:LONGEST] for word in phrase[:MOST]]
|
|
counts = _counts(meta.get("ss_tag_frequency"))
|
|
if not counts:
|
|
return []
|
|
least = max(counts.values()) * SHARE
|
|
shared = [tag for tag, count in counts.items() if count >= least and len(tag) <= LONGEST
|
|
and tag.lower().replace("_", " ") not in GENERIC and tag.lower() not in GENERIC]
|
|
return sorted(shared, key=lambda tag: -counts[tag])[:MOST]
|
|
|
|
|
|
def of_file(path):
|
|
"""The words of a LoRA file's header; [] for other kinds, other formats and unreadable files."""
|
|
fmt, header = read_head(path)
|
|
if fmt != "safetensors" or not header or classify(fmt, header)["kind"] != "loras":
|
|
return []
|
|
meta = header.get("__metadata__")
|
|
return from_meta(meta) if isinstance(meta, dict) else []
|